DrivenData Labs

DECEMBER 7, 2023

The challenge ¶ Falls are the leading cause of injury-related deaths among adults 65 and older. Fall risk can be mitigated through treatment of vision problems, exercise for strength and balance, removal of tripping hazards, and other interventions that appropriately target common fall causes. In the Unsupervised Wisdom Challenge , participants were tasked with identifying novel, effective methods of using unsupervised machine learning to extract insights about older adult falls from narrat

Natural Language Processing 130

Natural Language Processing Clustering Data Science Data Analysis 130

DrivenData Labs

NOVEMBER 28, 2023

In this guest post by MathWorks, we'll show you how to start working with satellite images to detect the presence of kelp in coastal areas.

130

130

DrivenData Labs

NOVEMBER 16, 2023

This is a follow-on post to a previous summary of the ways that organizations are using AI for climate action. It consolidates a range of real-world datasets from DrivenData challenges for anyone looking to get hands-on experience. Climate change poses a massive challenge, with far-reaching impacts. Many data scientists and developers are aware of the need for action and are interested in finding problems to take on.

AI 292

AI AI Machine Learning Machine Learning 292

DrivenData Labs

NOVEMBER 14, 2023

Our world is facing many urgent challenges, like climate change, water insecurity, and food insecurity. One critical tool for addressing these challenges is Earth observation data , meaning data that is gathered in outer space about life here on Earth! Earth observation data provide accurate information on our atmosphere, oceans, ecosystems, land cover, and built environment.

Python 162

Python AWS Azure Data Analysis 162

DrivenData Labs

SEPTEMBER 7, 2023

Hey! I'm Chris, and I'm a data scientist at DrivenData. I wanted to write this blog post because, while we work with satellite data frequently at DrivenData, I personally had not had that experience yet. Since I’m a beginner, I thought I would document the process of learning about satellite data to help others who are also trying to understand more about this data on their learning journeys.

Artificial Intelligence 130

Artificial Intelligence Artificial Intelligence Data Scientist 130

DrivenData Labs

AUGUST 8, 2023

Our team is excited to share a new feature that you will see in DrivenData competitions: Community Code! The Community Code section is a place where participants can share helpful code related to the competition. This could be anything from short snippets demonstrating some data processing to longer tutorials or analyses. Community Code will be enabled on a competition-by-competition basis.

Data Science 130

Data Science 130

DrivenData Labs

JULY 19, 2023

How can we use data and AI to help combat the effects of climate change? ¶ The current generation of humanity is faced with a massive challenge. The climate around us is changing, and how we mitigate and adapt to its effects will have deep and lasting impacts for ourselves, our children, other species, and the planet. A challenge of this magnitude calls for the best ideas, tools and technologies we have to offer.

AI 130

AI AI Machine Learning Machine Learning 130

DrivenData Labs

JUNE 19, 2023

The challenge ¶ The objective of the VisioMel Challenge was to explore the feasibility of an algorithm that can predict the recurrence of melanomas diagnosed at a localized stage. The results already show that the algorithms are at least on par with the traditional prognostic factors. In the near future, it will undoubtedly be possible to have a predictive digital signature of melanoma recurrence.

Deep Learning 130

Deep Learning Deep Learning Cross Validation Algorithm 130

DrivenData Labs

JUNE 14, 2023

Video Similarity Challenge ¶ Meet the top teams who identified copied and manipulated videos! ¶ Participants in the Meta AI Video Similarity Challenge found creative ways to improve representations used for copy detection, as well as localization techniques that allow copied sections to be identified efficiently within longer videos. Ed Pizzi, Meta AI Research Scientist and Video Similarity Challenge author The ability to identify and track content on social media platforms, called con

Supervised Learning 173

Supervised Learning Artificial Intelligence Artificial Intelligence AI 173

DrivenData Labs

MAY 24, 2023

The Challenge ¶ Motivation ¶ Coordinating our nation's airways is the role of the National Airspace System (NAS). The NAS is arguably the most complex transportation system in the world. Operational changes can save or cost airlines, taxpayers, consumers, and the economy at large thousands to millions of dollars on a regular basis. The NAS is investing in new ways to bring vast amounts of data together with state-of-the-art machine learning to improve air travel for everyone.

Machine Learning 225

Machine Learning Machine Learning Decision Trees Data Science 225

DrivenData Labs

MAY 18, 2023

The Community Spotlight celebrates the diversity of expertise, perspectives, and experiences of our community members. In this post we sit down with Dr. Helen Yannakoudakis, a winner of the Hateful Memes competition and an Assistant Professor at King’s College London, Visiting Researcher at the University of Cambridge, and co-founder and Chief Scientific Officer at Kinhub.

Natural Language Processing 211

Natural Language Processing Machine Learning Machine Learning Data Science 211

DrivenData Labs

MAY 18, 2023

The Community Spotlight celebrates the diversity of expertise, perspectives, and experiences of our community members. In this post we sit down with Brett Mullins, a winner of the Differential Privacy Temporal Map Challenge and a graduate student at the University of Massachusetts at Amherst. Name: Brett Mullins ¶ Hometown: Atlanta, Georgia ¶ Tell us a little about yourself.

Data Science 246

Data Science Data Scientist Machine Learning Machine Learning 246

DrivenData Labs

APRIL 13, 2023

The Challenge ¶ There are tens of thousands of lakes that matter for recreation and drinking water. Cyanobacterial blooms pose real risks in many of them, and we really don't know when or where they show up, except in the largest lakes. Satellites can help, but the high resolution satellites were not designed for this purpose, and simple methods to find these blooms will often mark features that aren't blooms.

Data Scientist 130

Data Scientist Decision Trees Algorithm Data Quality 130

DrivenData Labs

APRIL 3, 2023

Meet April ¶ On April 1st, DrivenData released a splashily-titled new competition: "Preview: The Future of DrivenData Competitions". The competition announced the debut of DrivenData's own chatbot, April, who was developed to take over evaluation of all competitions. If you tried submitting prediction to April, you likely found that she was very hard to impress.

Data Science 147

Data Science AI AI 147

DrivenData Labs

MARCH 30, 2023

Privacy-enhancing technologies (PETs) have the potential to unlock more trustworthy innovation in data analysis and machine learning. Federated learning is one such technology that enables organizations to analyze sensitive data while providing improved privacy protections. These technologies could advance innovation and collaboration in new fields and help harness the power of data to tackle some of our most pressing societal challenges.

Machine Learning 162

Machine Learning Machine Learning Data Science Algorithm 162

DrivenData Labs

MARCH 28, 2023

The Challenge ¶ “I believe that we are just at the beginning of the Earth Observation big data revolution. Joint effort and open science are the fundamental bricks to build new models and services for addressing societal challenges.” Dr. Andrea Nascetti, Faculty of Sciences, University of Liège Motivation ¶ Forests are adding and removing carbon dioxide from the air all the time.

Machine Learning 130

Machine Learning Machine Learning Cross Validation Deep Learning 130

DrivenData Labs

MARCH 27, 2023

VisioMel Challenge: Predicting Melanoma Relapse ¶ Welcome to the VisioMel Challenge: Predicting Melanoma Relapse ! In this benchmark blog post, we will show you how to load the data for the challenge, make a prediction, and package your materials for a submission. Along the way, we'll include some tips that might be useful as you improve on this benchmark model and help solve a critical problem in pathology and melanoma treatment.

Python 130

Python AWS 130

DrivenData Labs

MARCH 8, 2023

You may have heard there are new, modern standards in Python packaging ( pyproject.toml !) that have been adopted over the last few years. There are now several popular and shiny modern tools for managing your packaging projects. (Poetry! Hatch! PDM!) However, the documentation is scattered and much of it is specific to these competing tools. What are the recommended best practices when creating a Python package?

Python 246

Python 246

DrivenData Labs

FEBRUARY 21, 2023

Pushback to the Future: Predict Pushback Time at US Airports - Benchmark ¶ Coordinating our nation’s airways is the role of the National Airspace System (NAS). The NAS is one of the most complex transportation systems in the world. Operational changes can save or cost airlines, taxpayers, consumers, and the economy at large thousands to millions of dollars on a regular basis.

Machine Learning 130

Machine Learning Machine Learning Deep Learning Deep Learning 130

DrivenData Labs

FEBRUARY 2, 2023

Classifying New Zealand species Zamba's African forest model was trained with almost 250,000 videos from 14 countries in West, Central, and East Africa. Although the species that appear in these videos are exclusively African, this model can be used to classify videos from other parts of the world that contain species the model has never seen. To demonstrate, we'll use videos collected by the Takahē Recovery Programme in New Zealand.

Algorithm 130

Algorithm Data Science 130

DrivenData Labs

DECEMBER 11, 2022

In a previous blog post , we showed that we can use predictions from Zamba to classify videos from camera traps, keeping the ones that actually show animals and automatically removing the ones that are blank. For each video, Zamba generates a probability that it is blank. And these probabilities are generally well calibrated, so in a set of videos with probability 0.5, for example, the percentage that are blank is close to 50%.

Algorithm 130

Algorithm Python Data Science 130

DrivenData Labs

DECEMBER 13, 2022

How to Predict Harmful Algal Blooms Using LightGBM and Satellite Imagery ¶ Welcome to the benchmark notebook for the Tick Tick Bloom: Harmful Algal Bloom Detection Challenge ! If you are just getting starting, we recommended reading the competition homepage first. The goal of this benchmark is to: Demonstrate how to explore and work with the data Provide a basic framework for building a model Demonstrate how to package your work correctly for submission You can either expand on and improve

ML 130

ML ML Python Deep Learning 130

DrivenData Labs

JANUARY 11, 2023

The Challenge Mass spectrometers are now, and will continue to be, a key instrument for missions searching for life and habitability on other planets. The results of this GCMS challenge could not only support NASA scientists to more quickly analyze data, but is also a proof-of-concept of the use of data science and machine learning techniques on complex GCMS data for future missions.

Deep Learning 130

Deep Learning Deep Learning Machine Learning Machine Learning 130